v1.2.1

What's Changed

• [New Attack] ATT attack by @spencerwooo in #29
• [New Attack] GAMA: Generative Adversarial Multi-Object Scene Attacks by @spencerwooo in #30

Full Changelog: v1.2.0...v1.2.1

v1.2.0

What's Changed

• Docs by @spencerwooo in #27
• Update documentation and refactor attack creation process by @spencerwooo in #28

Potential Breaking Changes

In v1.2.0, the create_attack method accepts extra arguments to be passed onto the attack class as keyword arguments, instead of the original attack_args argument.

Full Changelog: v1.0.4...v1.2.0

v1.1.0

What's Changed

• [New Attack] NAA by @spencerwooo in #24
• Refactor content layout using HTML tables by @spencerwooo in #25
• [New Attack] ILPD by @spencerwooo in #26
• We are now on PyPI!

Full Changelog: v1.0.4...v1.1.0

v1.0.4

What's Changed

• [New Attack] Dispersion Reduction (DR) Attack by @spencerwooo in #21
• [New Attack] Learning Transferable Adversarial Perturbations (LTP) by @spencerwooo in #22
• Use hook_cfg for hooks and add VGG16 tests by @spencerwooo in #23
• AttackModel.from_pretrained() implement exact functional transform from torchvision

Full Changelog: v1.0.3...v1.0.4

v1.0.3

What's Changed

• Fix backward compatibility with Python 3.10

Full Changelog: v1.0.2...v1.0.3

v1.0.2

What's Changed

• Support for generative attacks by @spencerwooo in #20

Full Changelog: v1.0.1...v1.0.2

v1.0.1

What's Changed

• create_attack() method for creating an attack by its name.
• AttackModel.from_pretrained() method support specifying model source with prefix timm/ or tv/.
• Full unit testing for all attack methods.
• Docs in README updated.
• Version number pinned for recommended installation.

Weights of generative attacks

v1.0-weights

AttackModel support `timm/` and `tv/` prefix

v1.0.0

What's Changed

• DIFGSM fix input_diversity transform probability by @simone-dotolo in #15
• SSA DCT transform and num_spectrum not applied by @CHAOYUHONG in #13
• [New Attack] VDC Attack (Virtual Dense Connection) by @spencerwooo in #18
• Refactor for separate evaluation module by @spencerwooo in #19
• create_attack() and AttackModel.from_pretrained() helpers
• Full unit testing for most attacks

New Contributors

• @simone-dotolo made their first contribution in #15
• @CHAOYUHONG made their first contribution in #13

Full Changelog: v0.7.0...v1.0.0

v0.7.0

What's Changed

• DeCoWA (Deformation-Constrained Warping Attack) by @spencerwooo in #12

Full Changelog: v0.6.0...v0.7.0